Triple
T16861947
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sergius of Radonezh |
E409934
|
entity |
| Predicate | associatedWithPlace |
P2830
|
FINISHED |
| Object | Zagorsk |
E454063
|
NE FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Zagorsk | Statement: [Sergius of Radonezh, associatedWithPlace, Zagorsk]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Zagorsk Context triple: [Sergius of Radonezh, associatedWithPlace, Zagorsk]
-
A.
Zagorsk
chosen
Zagorsk is the former Soviet-era name of the Russian town now known as Sergiyev Posad, a major center of Orthodox Christianity northeast of Moscow.
-
B.
Pavlovo
Pavlovo is a historic town in Russia, known as an administrative center and for its traditional metalworking and handicraft industries.
-
C.
Pavlovo
Pavlovo is an urban-type settlement located within the Kirovsky District of Leningrad Oblast in northwestern Russia.
-
D.
Karlovo
Karlovo is a historic town in central Bulgaria, known as the birthplace of national hero Vasil Levski and as a gateway to the Balkan Mountains.
-
E.
Novi Grad
Novi Grad is the fictional capital city of the Eastern European nation Sokovia in the Marvel Cinematic Universe.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d88395e6c88190b22730f335107c14 |
completed | April 10, 2026, 4:59 a.m. |
| NER | Named-entity recognition | batch_69e3b5036e6c8190a3b9e525a34da2e1 |
completed | April 18, 2026, 4:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00bb274ba48190951acde0821e05a0 |
completed | May 10, 2026, 5:06 p.m. |
Created at: April 10, 2026, 5:24 a.m.